|
gptkbp:instance_of
|
gptkb:microprocessor
|
|
gptkbp:bfsLayer
|
7
|
|
gptkbp:bfsParent
|
gptkb:Squeeze_Net_1.1
|
|
gptkbp:based_on
|
Alex Net architecture
|
|
gptkbp:developed_by
|
gptkb:Deep_Scale
deep learning applications
|
|
gptkbp:has_achievements
|
high accuracy with fewer parameters
|
|
gptkbp:has_method
|
1.24 million
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Squeeze Net 1.2
|
|
gptkbp:is_adopted_by
|
startups
large companies
|
|
gptkbp:is_compared_to
|
gptkb:Shuffle_Net
gptkb:Mobile_Net
gptkb:Res_Net
|
|
gptkbp:is_compatible_with
|
gptkb:Graphics_Processing_Unit
gptkb:Py_Torch
|
|
gptkbp:is_designed_for
|
computer vision tasks
|
|
gptkbp:is_evaluated_by
|
gptkb:COCO_dataset
gptkb:Pascal_VOC_dataset
real-time applications
edge computing
resource-constrained environments
|
|
gptkbp:is_implemented_in
|
gptkb:Keras
gptkb:Caffe
|
|
gptkbp:is_known_for
|
low latency
high efficiency
fast inference speed
small model size
|
|
gptkbp:is_optimized_for
|
mobile and embedded devices
|
|
gptkbp:is_part_of
|
gptkb:Squeeze_Net_family
gptkb:Research_Institute
machine learning frameworks
computer vision libraries
|
|
gptkbp:is_supported_by
|
NVIDIAGP Us
TP Us
|
|
gptkbp:is_used_by
|
gptkb:physicist
gptkb:software
|
|
gptkbp:is_used_in
|
gptkb:Io_T_devices
gptkb:smartphone
gptkb:engine
gptkb:helicopter
image classification
object detection
semantic segmentation
|
|
gptkbp:release_date
|
gptkb:2018
|
|
gptkbp:successor
|
gptkb:Squeeze_Net_1.1
|
|
gptkbp:supports
|
transfer learning
|
|
gptkbp:training
|
gptkb:Image_Net_dataset
|
|
gptkbp:uses
|
fire modules
|
|
gptkbp:written_in
|
gptkb:Library
|